Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 130983
    Prev
    Next
    INDEX
    Explanations

    campaign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ironically
    -0.08
    fuscated
    -0.08
    evil
    -0.08
    iefer
    -0.07
     ordinary
    -0.07
     Stone
    -0.07
     eni
    -0.07
     Dora
    -0.07
    Mesa
    -0.07
     Atl
    -0.07
    POSITIVE LOGITS
     ach
    0.08
     dyn
    0.08
    ات
    0.07
     pelos
    0.07
    挑
    0.07
     Lady
    0.07
     campaigns
    0.07
     vague
    0.07
     devastating
    0.07
     tranh
    0.07
    Activations Density 0.011%

    No Known Activations